Discussion about stat consulting, stat packages, applied statistics and data analysis by statistical consultants of Academic Technology Services at UCLA. Please leave your comments or send us email at stattalk at ats.ucla.edu

Friday, January 19, 2007

Control Groups Gone Wild

This story goes back to my early days at ucla many years ago. I had a student that was studying test anxiety. She proposed dividing students, who were preparing to take their final exams in freshman science courses, into three groups. Group 1 would receive training in test taking skills, while Group 2 would meet in small groups and talk about their fears and how they deal with test anxiety. Group 3 was a do-nothing control group.

My clever idea was to create a placebo control group, that is, a group that receives some kind of treatment that is completely unrelated to test anxiety. To this end, I made a recording on cassette tape of various beeps coming out of my microwave oven. The tape was five minutes long and was played to groups of students who were told that the frequencies of the beeps were designed to influence brain wave patterns to reduce anxiety over the forth coming tests.

I won't keep you in suspense but you can probably guess the what the results were. The placebo control group had the greatest reduction in anxiety. In fact, the placebo group was significantly lower than either the test taking skills group (Group 1) or the talk therapy group (Group 2). Groups 1 and 2 were not significantly different from each other but both showed significant reduction in test anxiety over the do nothing control group.

My best guess is that we did too good of a job in selling the placebo control to the subjects. All was not lost however, we have been selling copies of the tape for over 25 years as an anxiety reduction treatment.

pbe

No comments:

Contributors